MULTI-SENSOR, AUTONOMOUS ROBOTIC VEHICLE WITH MAPPING CAPABILITY

• US 20170364090A1
• Filed: 12/17/2015
• Published: 12/21/2017
• Est. Priority Date: 12/17/2014
• Status: Active Grant

• Current Assignee: Husqvarna AB (HUSQVARNA)
• Original Assignee: Husqvarna AB (HUSQVARNA)
• Inventors: Grufman, Stefan, Mannefred, Bjrn, Forsberg, Hans
• Granted Patent: US 10,338,602 B2
• Time in Patent Office: Days
• CPC Class Codes: G01S 19/13 Receivers
• CPC Class Codes: G05D 1/0214 in accordance with safety or protection criteria, e.g. avoiding hazardous areas monitoring the location of vehicles within a certain area, e.g. forbidden or allowed areas, in traffic control systems for road vehicles G08G1/13
• CPC Class Codes: G05D 1/0274 using mapping information stored in a memory device navigation using map-matching G01C21/30

Abstract

A method for recording data from at least one sensor of a robotic vehicle responsive to the robotic vehicle transiting a portion of a parcel and determining a confidence score associated with the recorded data for each of a plurality of potential detection events. The confidence score may correspond to a probability that the recorded data corresponds to an object or feature. The method may further include generating map data comprising one or more objects or features correlated to potential detection events based at least in part on the confidence score of the respective objects or features.

Claims

1. A robotic vehicle comprising:

one or more functional components configured to execute a lawn care function;

a sensor network comprising one or more sensors configured to detect conditions proximate to the robotic vehicle; and

processing circuitry configurable to cause;

recording data from at least one sensor of a robotic vehicle responsive to the robotic vehicle transiting a portion of a parcel;

determining a confidence score associated with the recorded data for each of a plurality of potential detection events, the confidence score corresponding to a probability that the recorded data corresponds to an object or feature;

generating map data comprising one or more objects or features correlated to potential detection events based at least in part on the confidence score of the respective objects or features; and

determining the confidence score by recording an initial confidence score for an initial detection and an updated confidence score responsive to a second potential detection event at a same location as the initial detection.

4. The robotic vehicle of claim 1, wherein the plurality of sensors comprise at least a positioning device and an object detection device.

5. The robotic vehicle of claim 4, wherein the positioning device comprises an inertial measurement unit or a GPS receiver, and wherein the object detection device comprises a 2.5D sensor.

6. The robotic vehicle of claim 5, wherein the 2.5D sensor comprises a mobile time-of-flight measurement device.

8. The robotic vehicle of claim 1, wherein the processing circuitry is configured for generating the map data by comparing the confidence score of the one or more objects or features to a threshold and providing for inclusion of the corresponding one or more objects in a generated map responsive to the confidence score exceeding the threshold.

9. The robotic vehicle of claim 1, wherein the processing circuitry is further configured for classifying at least one of the one or more objects.

10. The robotic vehicle of claim 9, wherein the processing circuitry is configured for classifying the at least one of the one or more objects by comparing an image of the at least one of the one or more objects to known images to determine whether the image matches a known image of a classified object.

11. The robotic vehicle of claim 9, wherein the processing circuitry is configured for classifying the at least one of the one or more objects comprises determining whether the at least one of the one or more objects corresponds to grass.

2. (canceled)

3. (canceled)

7. (canceled)

12. A method comprising:

recording data from at least one sensor of a robotic vehicle responsive to the robotic vehicle transiting a portion of a parcel;

determining a confidence score associated with the recorded data for each of a plurality of potential detection events, the confidence score corresponding to a probability that the recorded data corresponds to an object or feature; and

generating map data comprising one or more objects or features correlated to potential detection events based at least in part on the confidence score of the respective objects or features,

wherein determining the confidence score comprises recording an initial confidence score for an initial detection and an updated confidence score responsive to a second potential detection event at a same location as the initial detection.

15. The method of claim 12, wherein the plurality of sensors comprise at least a positioning device and an object detection device.

16. The method of claim 15, wherein the positioning device comprises an inertial measurement unit or a GPS receiver, and wherein the object detection device comprises a 2.5D sensor.

17. The method of claim 16, wherein the 2.5D sensor comprises a mobile time-of-flight measurement device.

19. The method of claim 12, wherein generating the map data comprises comparing the confidence score of the one or more objects or features to a threshold and providing for inclusion of the corresponding one or more objects in a generated map responsive to the confidence score exceeding the threshold.

20. The method of claim 12, further comprising classifying at least one of the one or more objects.

21. The method of claim 20, wherein classifying the at least one of the one or more objects comprises comparing an image of the at least one of the one or more objects to known images to determine whether the image matches a known image of a classified object.

22. The method of claim 20, wherein classifying the at least one of the one or more objects comprises determining whether the at least one of the one or more objects corresponds to grass.

13. (canceled)

14. (canceled)

18. (canceled)